INDEX

Explanations

technical terms related to project management and software development

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

complete declarative sentences that state facts or describe information.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @trainjumperx

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 increa

-2.21

 affor

-2.20

 reluct

-2.19

 emphat

-2.17

 disagre

-2.17

 impra

-2.15

 viciss

-2.15

 scrat

-2.12

 guarante

-2.11

 coö

-2.09

POSITIVE LOGITS

 However

1.27

It

1.21

 This

1.19

 There

1.18

 Although

1.16

The

1.14

 While

1.13

In

1.12

As

1.12

 They

1.11

Activations Density 0.690%

technical terms related to project management and software development

complete declarative sentences that state facts or describe information.

No Comments

No Known Activations